###help(topic) - documentation on topic
help(runif)###?topic - id
is() - show objects in the search path; specify pat=“pat” to search on a pattern
a <- "troy"
is(a)? #not sure if this is rightdir() - show files in the current directory
getwd() #what working directory i am using## [1] "/Users/troy/Desktop/RclassJournal"dir() ## [1] "_site.yml" "CodeOp.html"
## [3] "CodeOp.Rmd" "Data Wrangling.Rmd"
## [5] "data_wrangle_assignment" "Data_Wrangling.html"
## [7] "docs" "figure"
## [9] "Final Tutorial.Rmd" "Final_Tutorial_files"
## [11] "Final_Tutorial.html" "GGPlot_files"
## [13] "GGPlot.html" "GGPlot.Rmd"
## [15] "histogram_lim_breaks.png" "images"
## [17] "index.html" "index.Rmd"
## [19] "Intrinsics.Rmd" "knitr-minimal.md"
## [21] "LabJournalWebsite.Rproj" "Links.Rmd"
## [23] "NOTES.Rmd" "Power Analysis.Rmd"
## [25] "README.md" "Rprof.out"
## [27] "Shiny_R_Class" "site_libs"
## [29] "Statistics.Rmd" "TroysRBasics_cache"
## [31] "TroysRBasics_files" "TroysRBasics.Rmd"
## [33] "xaringan"###list.files() - shows files in the directory
list.files()## [1] "_site.yml" "CodeOp.html"
## [3] "CodeOp.Rmd" "Data Wrangling.Rmd"
## [5] "data_wrangle_assignment" "Data_Wrangling.html"
## [7] "docs" "figure"
## [9] "Final Tutorial.Rmd" "Final_Tutorial_files"
## [11] "Final_Tutorial.html" "GGPlot_files"
## [13] "GGPlot.html" "GGPlot.Rmd"
## [15] "histogram_lim_breaks.png" "images"
## [17] "index.html" "index.Rmd"
## [19] "Intrinsics.Rmd" "knitr-minimal.md"
## [21] "LabJournalWebsite.Rproj" "Links.Rmd"
## [23] "NOTES.Rmd" "Power Analysis.Rmd"
## [25] "README.md" "Rprof.out"
## [27] "Shiny_R_Class" "site_libs"
## [29] "Statistics.Rmd" "TroysRBasics_cache"
## [31] "TroysRBasics_files" "TroysRBasics.Rmd"
## [33] "xaringan"###save() - saves the specified objects (…) in the XDR platform independent binary format
save() #i picked files form list but it is saying they arent found ###load() - load the datasets written with save
load(index.rmd) #says not found###data() - loads specified data sets
###library() - load add on packages from library
library(bitops) #loading according, box became checked in system library###read.table() - reads a file in table format and creates a data frame from it; the default separator sep="" is any whitespace; use header=TRUE to read the first line as a header of column names; use as.is=TRUE to prevent character vectors from being converted to factors; use comment.char="" to prevent “#” from being interpreted as a comment; use skip=n to skip n lines before reading data; see the help for options on row naming, NA treatment, and others
#???###read.csv() - (“filename”,header=TRUE) id. but with defaults set for reading comma-delimited files
myfile <- "troysdata.csv" #the data file i want to read
thedata <- read.csv(myfile, row.names=5)#only read row 5
print(thedata)###scan() - function read data from screen or file. Large data can be scanned in by just copy and paste, for example paste from EXCEL. Then use “ctrl+v” to paste the data, the data type will be automatically determined.
dir()## [1] "_site.yml" "CodeOp.html"
## [3] "CodeOp.Rmd" "Data Wrangling.Rmd"
## [5] "data_wrangle_assignment" "Data_Wrangling.html"
## [7] "docs" "figure"
## [9] "Final Tutorial.Rmd" "Final_Tutorial_files"
## [11] "Final_Tutorial.html" "GGPlot_files"
## [13] "GGPlot.html" "GGPlot.Rmd"
## [15] "histogram_lim_breaks.png" "images"
## [17] "index.html" "index.Rmd"
## [19] "Intrinsics.Rmd" "knitr-minimal.md"
## [21] "LabJournalWebsite.Rproj" "Links.Rmd"
## [23] "NOTES.Rmd" "Power Analysis.Rmd"
## [25] "README.md" "Rprof.out"
## [27] "Shiny_R_Class" "site_libs"
## [29] "Statistics.Rmd" "TroysRBasics_cache"
## [31] "TroysRBasics_files" "TroysRBasics.Rmd"
## [33] "xaringan"scan() #i dont see how this isnt found its clearly in the directory## numeric(0)###print() - prints its arguments; generic, meaning it can have different methods for different objects
a <- "hello"
print(a)## [1] "hello"###cat() - (…, file="“, sep=” ") prints the arguments after coercing to character; sep is the character separator between arguments
b <- c(1,2,3)
cat(b) #simply shows me whats in variabke (b)## 1 2 3###write.table() - prints x after converting to a data frame; if quote is TRUE,character or factor columns are surrounded by quotes ("); sep is the field separator; eol is the end-of-line separator; na is the string for missing values; use col.names=NA to add a blank column header to get the column headers aligned correctly for spreadsheet input
a <- data.frame(a=c(1,2,3),b=c(3,4,5)) #created a table
write.table(a,file="mytable.txt") #gave the file a name
#example list was saved in the notes document but i recently added it to the envirnment as a saved variable##DATA CREATION
###c() - combine arguements by forming a vector, if recursive=TRUE is used it will descend through lists combining all elements in one vector
first_names <- c("asdasas", "fwefef", "sfweg")
write.table(first_names)## "x"
## "1" "asdasas"
## "2" "fwefef"
## "3" "sfweg"###from:to (where from and to are replaced with numbers, e.g. 1:10)
a <- (1:5)
a## [1] 1 2 3 4 5###seq() - generates a sequence by= specifies increment, length= specifies how long
seq(2:10, by = 2) # i esentially want to show only even numbers the by= isnt doing what i think it should
seq(2:10, by = (1))###rep() - used to replicate. replicate x times; use each= to repeat “each” element of x each times; rep(c(1,2,3),2) is 1 2 3 1 2 3; rep(c(1,2,3),each=2) is 1 1 2 2 3 3
rep(c(1,2,3),each=2)## [1] 1 1 2 2 3 3###data.frame - create a data frame of the named or unnamed arguments; data.frame(v=1:4,ch=c(“a”,“B”,“c”,“d”),n=10);shorter vectors are recycled to the length of the longest
###list() - create a list of the named or unnamed arguments
a <- list(a=1,2,3,b="hello",d=2,3,4)
b <- list(a=2, b="hi", d=3)
print(a)## $a
## [1] 1
##
## [[2]]
## [1] 2
##
## [[3]]
## [1] 3
##
## $b
## [1] "hello"
##
## $d
## [1] 2
##
## [[6]]
## [1] 3
##
## [[7]]
## [1] 4print(b)## $a
## [1] 2
##
## $b
## [1] "hi"
##
## $d
## [1] 3###matrix() - build a matrix
h <- matrix(1:20, nrow=5, ncol=5)
View(h)###factor() - encodes a vector x as a factor
sodium <- factor(c("low", "med", "high"))
levels(sodium)## [1] "high" "low" "med"sodium <- factor(sodium, levels=c("low", "med", "high"), ordered=TRUE)
levels(sodium)## [1] "low" "med" "high"min(sodium)## [1] low
## Levels: low < med < high###rbind() - combine data/info by rows for matrices, data frames, etc. must have equivalent amount of rows, if not equate them by adding NA to either until same qty is reached
###cbind() - combine data by columns same rules apply as rbind
##Slicing and Extracting Data - indexing Vectors ### x[n] - what/remove is in this position in the matrix
a = matrix(
c(2, 4, 3, 1, 5, 7), # the data elements
nrow=2, # number of rows
ncol=3, # number of columns
byrow = TRUE) # fill matrix by rows
a # print the matrix ## [,1] [,2] [,3]
## [1,] 2 4 3
## [2,] 1 5 7a[2 , 1] # first thing in second row## [1] 1###x[-n] - everything but what is in the [] position
a = matrix(
c(2, 4, 3, 1, 5, 7), # the data elements
nrow=2, # number of rows
ncol=3, # number of columns
byrow = TRUE) # fill matrix by rows
a # print the matrix ## [,1] [,2] [,3]
## [1,] 2 4 3
## [2,] 1 5 7a[-2, ] # everything but the first thing in the second row## [1] 2 4 3a = matrix(
c(2, 4, 3, 1, 5, 7), # the data elements
nrow=2, # number of rows
ncol=3, # number of columns
byrow = TRUE) # fill matrix by rows
a # print the matrix ## [,1] [,2] [,3]
## [1,] 2 4 3
## [2,] 1 5 7a[1:2, c(1,1,1,1,1)] # everything but the first thing in the second row## [,1] [,2] [,3] [,4] [,5]
## [1,] 2 2 2 2 2
## [2,] 1 1 1 1 1a = matrix(
c(2, 4, 3, 1, 5, 7), # the data elements
nrow=2, # number of rows
ncol=3, # number of columns
byrow = TRUE) # fill matrix by rows
a [-(1:3)] # print the matrix ## [1] 5 3 7a = matrix(
c(2, 4, 3, 1, 5, 7), # the data elements
nrow=2, # number of rows
ncol=3, # number of columns
byrow = TRUE) # fill matrix by rows
a[c(1,3,5)] #what is in postion 1,3,5## [1] 2 4 3k <- matrix(1:9, nrow = 3 dimnames = list(
c("row1", "row2"), # row names
c("col1", "col2", "col3")) # column names
k #print A
# element at 2nd row, 3rd column ###x[x>3] all elements greater than 3 -
x <- c(1,3,4,5,6,7)
x[x > 3] ## [1] 4 5 6 7###x[x > 3 & x < 5] all elements between 3 and 5
x <- c(1,3,4,5,6,7)
x[x > 3 & x < 5] ## [1] 4###x[x %in% c(“a”,“and”,“the”)] all elements in given set
##Indexing lists
###x[n] list with elements n
n <- c(2, 3, 5)
s <- c("aa", "bb", "cc", "dd", "ee")
b <- c(TRUE, FALSE, TRUE, FALSE, FALSE)
x <- list(n, s, b, 3) # x contains copies of n, s, b
x[4]## [[1]]
## [1] 3###x[[n]] nt h element of the list -
n <- c(2, 3, 5)
s <- c("aa", "bb", "cc", "dd", "ee")
b <- c(TRUE, FALSE, TRUE, FALSE, FALSE)
x <- list(n, s, b, 3) # x contains copies of n, s, b
x[[1]][2]## [1] 3###x[[“name”]] element of the list named “name”
b[[TRUE]]## [1] TRUE###x$name id.
bob <- c(2, 3, 5)
john <- c("aa", "bb")
v <- list(bob <- c(2, 3, 5), john <- c("aa", "bb"))
v$bob #i expect this to return 2,3,5## NULLv[bob]## [[1]]
## [1] "aa" "bb"
##
## [[2]]
## NULL
##
## [[3]]
## NULL##Indexing matrices
###x[y,b] element at row y, column b
x <- matrix(1:9, nrow = 3, dimnames = list(c("X","Y","Z"), c("A","B","C")))
x## A B C
## X 1 4 7
## Y 2 5 8
## Z 3 6 9x["Y","B"]## [1] 5###x[“Z”,] row Z
x["Z",]## A B C
## 3 6 9###x[,c] column
x[,"C"]## X Y Z
## 7 8 9###x[,c(“A”,“C”)] columns A and C
x[,c("A","C")]## A C
## X 1 7
## Y 2 8
## Z 3 9###x[“name”,] row named “name”
x["Y",]## A B C
## 2 5 8##Indexing data frames (matrix indexing plus the following)
###x[[“name”]] column named “name”
x <- matrix(1:9, nrow = 3, dimnames = list(c("X","Y","Z"), c("A","B","C")))
x[["B"]]###x$named
##Variable conversion ###as.data.frame(x) -
as.data.frame(x, row.names=NULL, optional=FALSE, xy=FALSE,
na.rm=FALSE, long=FALSE, ...)#not sure exactly what i am attempting to do here###as.numeric(x) -
x <- c(1,2,4,5,53,2)
as.numeric(x)# i believe this is should be coding responses as numeric, which i dont quite undetstand in this context.for instance a likert scale ## [1] 1 2 4 5 53 2###as.logical(x)
###as.character(x)
##Variable information
###is.na(x)
###is.null(x)
###is.data.frame(x)
###is.numeric(x)
###is.character(x)
###length(x)
x <- c(1,2,5,6,3,6,64,4,3,7,8,9)
length(x)## [1] 12###dim(x)
x <- c(1,2,5,6,3,6,64,4,3,7,8,9)
dim(x)#? not sure here## NULL###dimnames(x)
###nrow(x)ncol(x) - amount of col/rows, also to use name
matrix(a, nrow = 2, ncol = 3)## [,1] [,2] [,3]
## [1,] 2 4 3
## [2,] 1 5 7###class()
###attributes()
##Data selection and manipulation
###which.max() - returns the largest number
x <- c(1,4,57,54754,6576,3456346,4)
which.max(x) #not sure why its not diagnosing thr enetire number and just the last digit, ## [1] 6###which.min() - smallest element of
x <- c(1211,124,57,54754,6576,3456346,4)
which.min(x) #why is this not 4?## [1] 7###which() - what postion something is in
y <- c(3,5,7,8,4,3,3,2)
which(y == 4)## [1] 5###sort() - puts things in order
m <- c(5,2,6,7,8,3,3,3,3)
sort(m)## [1] 2 3 3 3 3 5 6 7 8###unique()
###table() - can be used for frequency tables
d <- c(2,4,5,8,5,3,6,5,8,6,5,3,3,4,6,6,8,8,5,4,3,2,3)
table(d)#, or categorization, assuming i can use strsplit but im not positive## d
## 2 3 4 5 6 8
## 2 5 3 5 4 4###sample - simply put to sample numbers, but you can modify to sample greater or less then and incorporate sort to clean it up
d <- 1:20
sort(sample(d[d > 7]))#sorted all numbers greater than 7 from variable d## [1] 8 9 10 11 12 13 14 15 16 17 18 19 20##MATH
###max() - largest number in variable
max(d)## [1] 20###min() - smallest number in variable
min(d)## [1] 1###range() - from smallest to largest number
range(d)## [1] 1 20###sum - sum of all integers of a given variable
sum(d)## [1] 210###mean
mean(d)## [1] 10.5###median
median(d)## [1] 10.5###var - The average of the squared differences from the Mean
var(d)## [1] 35###sd - Standard Deviation is just the square root of Variance
sd(d)## [1] 5.91608###cor -
n <- c(2,2,4,4,6,6,6,3,3,3,3)
cor(d,n)#just not sure here abount what to do###round() - specify whole or decimal numbers in a sequence or within a variable
round(.5 + -2:4)## [1] -2 0 0 2 2 4 4( x1 <- seq(-2, 4, by = .5) )#sequence of numbers by the .5 in each sequence ## [1] -2.0 -1.5 -1.0 -0.5 0.0 0.5 1.0 1.5 2.0 2.5 3.0 3.5 4.0###abs() -
abs(d)## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20x <- matrix(c(-3,5,-7,1,-9,4),nrow=3,ncol=2,byrow=TRUE)
abs(x[1,])#absolute value of row one## [1] 3 5##Matrices
###t()
h <- matrix(1:20, nrow=5, ncol=4)
t(h)## [,1] [,2] [,3] [,4] [,5]
## [1,] 1 2 3 4 5
## [2,] 6 7 8 9 10
## [3,] 11 12 13 14 15
## [4,] 16 17 18 19 20###diag() - not sure what this is
# NOT RUN {
dim(diag(3))## [1] 3 3diag(10, 3, 4) # guess what?## [,1] [,2] [,3] [,4]
## [1,] 10 0 0 0
## [2,] 0 10 0 0
## [3,] 0 0 10 0all(diag(1:3) == {m <- matrix(0,3,3); diag(m) <- 1:3; m})## [1] TRUE###rowsums() / colsums() - sum of rows and columns. rowmeans() / Colmeans()
h <- matrix(1:20, nrow=5, ncol=4)
rowSums(h)## [1] 34 38 42 46 50colSums(h)## [1] 15 40 65 90rowMeans(h)## [1] 8.5 9.5 10.5 11.5 12.5colMeans(h)## [1] 3 8 13 18##Advanced data processing ###apply
apply###aggregate()
#not sure why or what this is going to do for me ##Strings
###paste()
paste0(1:12) #need an elementary explanation## [1] "1" "2" "3" "4" "5" "6" "7" "8" "9" "10" "11" "12"paste(1:12) ## [1] "1" "2" "3" "4" "5" "6" "7" "8" "9" "10" "11" "12"as.character(1:12)## [1] "1" "2" "3" "4" "5" "6" "7" "8" "9" "10" "11" "12"###strsplit - strsplit helps find letters in string
q <- "dogs cats" #strsplit helps find letters in string
strsplit(q,split="") #to split a character vector## [[1]]
## [1] "d" "o" "g" "s" " " "c" "a" "t" "s"t <-strsplit(q,split ="")
t[[1]]## [1] "d" "o" "g" "s" " " "c" "a" "t" "s"t[[1]][2]#use to access second item in string## [1] "o"t[[1]][6]#use to access sixth item in string## [1] "c"table(t)## t
## a c d g o s t
## 1 1 1 1 1 1 2 1###tolower() -
test1 <- c(text1 = "England and France are members of NATO and UNESCO",
text2 = "NASA sent a rocket into space.")
tolower(test1)## text1
## "england and france are members of nato and unesco"
## text2
## "nasa sent a rocket into space."###toupper() -
test1 <- c(text1 = "England and France are members of NATO and UNESCO",
text2 = "NASA sent a rocket into space.")
toupper(test1)## text1
## "ENGLAND AND FRANCE ARE MEMBERS OF NATO AND UNESCO"
## text2
## "NASA SENT A ROCKET INTO SPACE."##Plotting
###hist()
v <- c(3, 4, 7, 6, 5, 1, 4, 3, 4, 4, 5, 4, 0, 3, 5, 4, 4, 4)
# Give the chart file a name.
png(file = "histogram_lim_breaks.png")
# Create the histogram.
hist(v,xlab = "Weight",col = "green",border = "red", xlim = c(0,8), ylim = c(0,10),
breaks = 5)###plot()
v <- c(3, 4, 7, 6, 5, 1, 4, 3, 4, 4, 5, 4, 0, 3, 5, 4, 4, 4)
# Give the chart file a name.
png(file = "histogram_lim_breaks.png")
# Create the histogram.
plot(v,xlab = "Weight",col = "green", xlim = c(0,8), ylim = c(0,10))##Distributions
###rnorm - generates random deviates.
rnorm(n, mean = 10, sd = 1.5)## [1] 8.339255 10.111573 9.808169###runif - random numbers
n <- c(1,2,5,7,8,4,3,2,5,6,8,8,5)
runif(n, min = 0, max = 10)## [1] 9.5623557 8.7015802 3.1562935 7.9581245 0.4789979 8.9265102 9.5411924
## [8] 6.2046301 0.8220830 9.5295412 2.6235542 7.0328795 4.2676212##Programming
###show that you can define a function
addtwo <- function(x) {
b <- x + 2
return(b)
}
addtwo(2) ## [1] 4sumsq <- function(x,y) {
x^2 + y^2
}
sumsq(2,3)#i think i need to insert a table to truly make this work ## [1] 13###show that you can write a for loop
###show that you can write a while loop
x <- 4
while(x < 100) {
x <- x + 8
print(x)
}## [1] 12
## [1] 20
## [1] 28
## [1] 36
## [1] 44
## [1] 52
## [1] 60
## [1] 68
## [1] 76
## [1] 84
## [1] 92
## [1] 100###show that you can write an if else statement
j = c(1:30)
ifelse(j %% 3 == 0, "three", "not")## [1] "not" "not" "three" "not" "not" "three" "not" "not"
## [9] "three" "not" "not" "three" "not" "not" "three" "not"
## [17] "not" "three" "not" "not" "three" "not" "not" "three"
## [25] "not" "not" "three" "not" "not" "three"###Explain what return() does inside a function, show you can use it
check <- function(x) {
if (x > 0) {
result <- "Positive"
}
else if (x < 0) {
result <- "Negative"
}
else {
result <- "Zero"
}
return(result)
}
check(1)## [1] "Positive"check(-3)## [1] "Negative"check(0)## [1] "Zero"###Explain what break() does, show you can use it